ISDFS Talk: Robots that ask for help: Conformal Prediction for LLM Planners

Talk at the International Seminar on Distribution-Free Statistics

Title:
Robots That Ask For Help: Conformal Prediction for LLM Planners

Abstract:
Large language models (LLMs) exhibit a wide range of promising capabilities --- from step-by-step planning to commonsense reasoning --- that may provide utility for robots, but remain prone to confidently hallucinated predictions. In this talk, I will present KnowNo: a framework for measuring and aligning the uncertainty of LLM-based planners, such that they know when they don't know, and ask for help when needed. KnowNo builds on the theory of conformal prediction to provide statistical guarantees on generalization while minimizing human help in complex multi-step planning settings. Experiments across a variety of simulated and real robot setups that involve tasks with different modes of ambiguity show that KnowNo performs favorably over modern baselines in terms of improving efficiency and autonomy, while providing formal assurances. KnowNo can be used with LLMs out-of-the-box without model-finetuning, and suggests a promising lightweight approach to modeling uncertainty that can complement and scale with the growing capabilities of foundation models.